A Data-Driven Damage Identification Framework Based on Transmissibility Function Datasets and One-Dimensional Convolutional Neural Networks: Verification on a Structural Health Monitoring Benchmark Structure

被引:55
作者
Liu, Tongwei [1 ]
Xu, Hao [2 ,3 ]
Ragulskis, Minvydas [4 ]
Cao, Maosen [1 ]
Ostachowicz, Wieslaw [5 ]
机构
[1] Hohai Univ, Dept Engn Mech, Nanjing 210098, Peoples R China
[2] Dalian Univ Technol, Fac Vehicle Engn & Mech, Sch Aeronaut & Astronaut, State Key Lab Struct Anal Ind Equipment, Dalian 116024, Peoples R China
[3] Northwestern Univ, Dept Civil & Environm Engn, Chicago, IL 60626 USA
[4] Kaunas Univ Technol, Ctr Nonlinear Syst, Studentu 50-146, LT-51368 Kaunas, Lithuania
[5] Polish Acad Sci, Inst Fluid Flow Machinery, PL-80231 Gdansk, Poland
基金
国家重点研发计划;
关键词
structural health monitoring; damage identification; transmissibility function; convolutional neural networks; deep learning; SUPPORT VECTOR MACHINE; FAULT-DIAGNOSIS; SENSOR;
D O I
10.3390/s20041059
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Vibration-based data-driven structural damage identification methods have gained large popularity because of their independence of high-fidelity models of target systems. However, the effectiveness of existing methods is constrained by critical shortcomings. For example, the measured vibration responses may contain insufficient damage-sensitive features and suffer from high instability under the interference of random excitations. Moreover, the capability of conventional intelligent algorithms in damage feature extraction and noise influence suppression is limited. To address the above issues, a novel damage identification framework was established in this study by integrating massive datasets constructed by structural transmissibility functions (TFs) and a deep learning strategy based on one-dimensional convolutional neural networks (1D CNNs). The effectiveness and efficiency of the TF-1D CNN framework were verified using an American Society of Civil Engineers (ASCE) structural health monitoring benchmark structure, from which dynamic responses were captured, subject to white noise random excitations and a number of different damage scenarios. The damage identification accuracy of the framework was examined and compared with others by using different dataset types and intelligent algorithms. Specifically, compared with time series (TS) and fast Fourier transform (FFT)-based frequency-domain signals, the TF signals exhibited more significant damage-sensitive features and stronger stability under excitation interference. The utilization of 1D CNN, on the other hand, exhibited some unique advantages over other machine learning algorithms (e.g., traditional artificial neural networks (ANNs)), particularly in aspects of computation efficiency, generalization ability, and noise immunity when treating massive, high-dimensional datasets. The developed TF-1D CNN damage identification framework was demonstrated to have practical value in future applications.
引用
收藏
页数:25
相关论文
共 48 条
  • [1] 1-D CNNs for structural damage detection: Verification on a structural health monitoring benchmark data
    Abdeljaber, Osama
    Avci, Onur
    Kiranyaz, Mustafa Serkan
    Boashash, Boualem
    Sodano, Henry
    Inman, Daniel J.
    [J]. NEUROCOMPUTING, 2018, 275 : 1308 - 1317
  • [2] Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks
    Abdeljaber, Osama
    Avci, Onur
    Kiranyaz, Serkan
    Gabbouj, Moncef
    Inman, Daniel J.
    [J]. JOURNAL OF SOUND AND VIBRATION, 2017, 388 : 154 - 170
  • [3] Structural Damage Detection in Real Time: Implementation of 1D Convolutional Neural Networks for SHM Applications
    Avci, Onur
    Abdeljaber, Osama
    Kiranyaz, Serkan
    Inman, Daniel
    [J]. STRUCTURAL HEALTH MONITORING & DAMAGE DETECTION, VOL 7, 2017, : 49 - 54
  • [4] Modal identification and damage detection using the data-driven stochastic subspace and ARMAV methods
    Bodeux, JB
    Golinval, JC
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2003, 17 (01) : 83 - 89
  • [5] Detection of bolt load loss in hybrid composite/metal bolted connections
    Caccese, V
    Mewer, R
    Vel, SS
    [J]. ENGINEERING STRUCTURES, 2004, 26 (07) : 895 - 906
  • [6] A robust Bayesian methodology for damage localization in plate-like structures using ultrasonic guided-waves
    Cantero-Chinchilla, Sergio
    Chiachio, Juan
    Chiachio, Manuel
    Chronopoulos, Dimitrios
    Jones, Arthur
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2019, 122 : 192 - 205
  • [7] Neural network ensemble-based parameter sensitivity analysis in civil engineering systems
    Cao, M. S.
    Pan, L. X.
    Gao, Y. F.
    Novak, D.
    Ding, Z. C.
    Lehky, D.
    Li, X. L.
    [J]. NEURAL COMPUTING & APPLICATIONS, 2017, 28 (07) : 1583 - 1590
  • [8] HierarchicalWavelet-Aided Neural Intelligent Identification of Structural Damage in Noisy Conditions
    Cao, Mao-Sen
    Ding, Yu-Juan
    Ren, Wei-Xin
    Wang, Quan
    Ragulskis, Minvydas
    Ding, Zhi-Chun
    [J]. APPLIED SCIENCES-BASEL, 2017, 7 (04):
  • [9] Improved hybrid wavelet neural network methodology for time-varying behavior prediction of engineering structures
    Cao, Maosen
    Qiao, Pizhong
    Ren, Qingwen
    [J]. NEURAL COMPUTING & APPLICATIONS, 2009, 18 (07) : 821 - 832
  • [10] Damage detection using data-driven methods applied to moving-load responses
    Cavadas, Filipe
    Smith, Ian F. C.
    Figueiras, Joaquim
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2013, 39 (1-2) : 409 - 425